检索结果-南通市图书馆

Dense Face Network:A Dense Face Detector Based on Global Context and Visual Attention mechanism

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2022年第3期19卷 247-256页

作者： Lin Song Jin-Fu Yang Qing-Zhen Shang Ming-Ai Li Faculty of Information Technology Beijing University of TechnologyBeijing 100124China Beijing Key Laboratory of Computational Intelligence and Intelligent Systems Beijing 100124China

Face detection has achieved tremendous strides thanks to convolutional neural networks. However, dense face detection remains an open challenge due to large face scale variation, tiny faces, and serious occlusion. This paper presents a robust, dense face detector using global context and visual Attention mechanisms which can significantly improve detection accuracy. Specifically, a global context fusion module with top-down feedback is proposed to improve the ability to identify tiny faces. Moreover, a visual Attention mechanism is employed to solve the problem of occlusion. Experimental results on the public face datasets WIDER FACE and FDDB demonstrate the effectiveness of the proposed method.

关键词： Face detection global context Attention mechanism computer vision deep learning

维普期刊数据库

Double-branch fusion network with a parallel attention selection mechanism for camouflaged object detection

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2023年第6期66卷 258-266页

作者： Junjiang XIANG Qing PAN Zhengrong ZHANG Songnian FU Yuwen QIN Advanced Institute of Photonics Technology School of Information EngineeringGuangdong University of Technology Guangdong Provincial Key Laboratory of Photonics Information Technology Guangdong University of Technology Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Electronics and InformationGuangxi University

To meet the challenge of camouflaged object detection (COD),which has a high degree of intrinsic similarity between the object and background,this paper proposes a double-branch fusion network(DBFN)with a parallel attention selection mechanism (PASM).In detail,a schismatic receptive field block(SRF)combined with an Attention mechanism for low-level information is performed to learn texture features in one branch,and an integration of the SRF,a hybrid Attention mechanism (HAM),and a depth feature polymerization module (DFPM)is employed for high-level information to extract detection features in the other branch.Then,both texture features and detection features are input into the PASM to acquire selective expression matrices.Eventually,the final result is obtained after further selective matrix optimization with atrous spatial pyramid pooling (ASPP)and a residual channel attention block (RCAB)being applied serially.Experimental results on three public datasets verify that our method outperforms the state-of-the-art methods in terms of four evaluation metrics,i.e.,mean absolute error (MAE),weighted F βmeasure (Fβω),structural measure (Sα),and E-measure (Eφ)

关键词： camouflaged object detection Attention mechanism feature extraction feature aggregation texture information fuzzy boundary

An Image Fingerprint and Attention mechanism Based Load Estimation Algorithm for Electric Power System

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第7期140卷 577-591页

作者： Qing Zhu Linlin Gu Huijie Lin Electricity Technology Branch Nari Technology Co.Ltd.Nanjing211106China NARI-TECH Nanjing Control Systems Co. Ltd.Nanjing211106China

With the rapid development of electric power systems,load estimation plays an important role in system operation and planning.Usually,load estimation techniques contain traditional,time series,regression analysis-based,and machine learning-based estimation.Since the machine learning-based method can lead to better performance,in this paper,a deep learning-based load estimation algorithm using image fingerprint and Attention mechanism is proposed.First,an image fingerprint construction is proposed for training data.After the data preprocessing,the training data matrix is constructed by the cyclic shift and cubic spline interpolation.Then,the linear mapping and the gray-color transformation method are proposed to form the color image fingerprint.Second,a convolutional neural network(CNN)combined with an attentionmechanism is proposed for training performance improvement.At last,an experiment is carried out to evaluate the estimation performance.Compared with the support vector machine method,CNN method and long short-term memory method,the proposed algorithm has the best load estimation performance.

关键词： Load estimation deep learning Attention mechanism image fingerprint construction

A novel intrusion detection model for the CAN bus packet of in-vehicle network based on Attention mechanism and autoencoder

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Digital Communications and Networks 2023年第1期9卷 14-21页

作者： Pengcheng Wei Bo Wang Xiaojun Dai Li Li Fangcheng He School of Mathematics and Information Engineering Chongqing University of EducationChongqingChina School of Automation Chongqing University of Posts and TelecommunicationsChongqingChina Department of Modern Service Chongqing Energy Industry Technician CollegeChongqingChina College of Foreign Languages Literature Chongqing University of EducationChongqingChina

The attacks on in-vehicle Controller Area Network(CAN)bus messages severely disrupt normal communication between vehicles.Therefore,researches on intrusion detection models for CAN have positive business value for vehicle security,and the intrusion detection technology for CAN bus messages can effectively protect the invehicle network from unlawful attacks.Previous machine learning-based models are unable to effectively identify intrusive abnormal messages due to their inherent shortcomings.Hence,to address the shortcomings of the previous machine learning-based intrusion detection technique,we propose a novel method using Attention mechanism and AutoEncoder for Intrusion Detection(AMAEID).The AMAEID model first converts the raw hexadecimal message data into binary format to obtain better input.Then the AMAEID model encodes and decodes the binary message data using a multi-layer denoising autoencoder model to obtain a hidden feature representation that can represent the potential features behind the message data at a deeper level.Finally,the AMAEID model uses the Attention mechanism and the fully connected layer network to infer whether the message is an abnormal message or not.The experimental results with three evaluation metrics on a real in-vehicle CAN bus message dataset outperform some traditional machine learning algorithms,demonstrating the effectiveness of the AMAEID model.

关键词： Controller area network bus packet In-vehicle network Attention mechanism Autoencoder

Prediction of Listed Company Innovation Ability Based on Attention mechanism

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of the Operations Research Society of China 2023年第1期11卷 177-187页

作者： Huan-Yu Ma Yan Xu Yu-Long Liu Department of Information and Computer Science University of Science and Technology BeijingBeijing100083China No.15 Research Institute China Electronics Technology Group CorporationBeijing100083China

Innovation is the center of the enterprise development, which is the main driving force of enterprises’ competitiveness. To evaluate the enterprises’ innovation ability, we firstly establish an index system which aims at analyzing the enterprise innovation ability. We also retrieve the data of the listed companies in Wind database from 2015 to 2019 and label them using factor analysis method. Then, a new deep learning classificational framework with Attention mechanism and LSTM is established. The results show that when Attention mechanism and LSTM are added into the convolutional neural network(CNN), the model’s prediction performance is better improved, and the accuracy, recall, precision and F-score are 0.914, 0.914, 0.916 and 0.915, respectively. This indicates the strong generalization ability of our new model. Finally, we also find that patents and R &D expenditures are the most important factor affecting the corporate innovation ability through SHapley Additive exPlanations(SHAP). Companies with more patents and R &D expenditures are generally considered to be more innovative.

关键词： Corporate innovation ability convolutional neural network Attention mechanism long short-term memory

Building Indoor Dangerous Behavior Recognition Based on LSTM-GCN with Attention mechanism

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2023年第11期137卷 1773-1788页

作者： Qingyue Zhao Qiaoyu Gu Zhijun Gao Shipian Shao Xinyuan Zhang School of Management Shenyang Jianzhu UniversityShenyang110168China School of Information and Communication Engineering North University of ChinaTaiyuan030051China School of Information and Control Engineering Shenyang Jianzhu UniversityShenyang110168China

Building indoor dangerous behavior recognition is a specific application in the field of abnormal human recognition.A human dangerous behavior recognition method based on LSTM-GCN with Attention mechanism(GLA)model was proposed aiming at the problem that the existing human skeleton-based action recognition methods cannot fully extract the temporal and spatial features.The network connects GCN and LSTMnetwork in series,and inputs the skeleton sequence extracted by GCN that contains spatial information into the LSTM layer for time sequence feature extraction,which fully excavates the temporal and spatial features of the skeleton sequence.Finally,an attention layer is designed to enhance the features of key bone points,and Softmax is used to classify and identify dangerous behaviors.The dangerous behavior datasets are derived from NTU-RGB+D and Kinetics data sets.Experimental results show that the proposed method can effectively identify some dangerous behaviors in the building,and its accuracy is higher than those of other similar methods.

关键词： Human skeleton building indoor dangerous behaviors recognition graph convolution network long short term memory network Attention mechanism

Multiscale feature learning and Attention mechanism for infrared and visible image fusion

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2024年第2期67卷 408-422页

作者： GAO Li LUO DeLin WANG Song School of Aerospace Engineering Xiamen UniversityXiamen 361102China Electric Power Research Institute China Southern Power GridGuangzhou 510063China

Current fusion methods for infrared and visible images tend to extract features at a single scale,which results in insufficient detail and incomplete feature preservation.To address these issues,we propose an infrared and visible image fusion network based on a multiscale feature learning and Attention mechanism(MsAFusion).A multiscale dilation convolution framework is employed to capture image features across various scales and broaden the perceptual scope.Furthermore,an attention network is introduced to enhance the focus on salient targets in infrared images and detailed textures in visible images.To compensate for information loss during convolution,jump connections are utilized during the image reconstruction phase.The fusion process utilizes a combined loss function consisting of pixel loss and gradient loss for unsupervised fusion of infrared and visible images.Extensive experiments on the dataset of electricity facilities demonstrate that our proposed method outperforms nine state-of-theart methods in terms of visual perception and four objective evaluation metrics.

关键词： infrared and visible images image fusion Attention mechanism CNN feature extraction

维普期刊数据库

Event Temporal Relation Extraction with Attention mechanism and Graph Neural Network

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2022年第1期27卷 79-90页

作者： Xiaoliang Xu Tong Gao Yuxiang Wang Xinle Xuan the Department of Computer Science and Engineering Hangzhou Dianzi UniversityHangzhou 310018China the Hangzhou Sanhui Digital Information Technology Co. Ltd.Hangzhou 310018China

Event temporal relation extraction is an important part of natural language processing.Many models are being used in this task with the development of deep learning.However,most of the existing methods cannot accurately obtain the degree of association between different tokens and events,and event-related information cannot be effectively integrated.In this paper,we propose an event information integration model that integrates event information through multilayer bidirectional long short-term memory(Bi-LSTM)and Attention mechanism.Although the above scheme can improve the extraction performance,it can still be further optimized.To further improve the performance of the previous scheme,we propose a novel relational graph attention network that incorporates edge attributes.In this approach,we first build a semantic dependency graph through dependency parsing,model a semantic graph that considers the edges’attributes by using top-k Attention mechanisms to learn hidden semantic contextual representations,and finally predict event temporal relations.We evaluate proposed models on the TimeBank-Dense dataset.Compared to previous baselines,the Micro-F1 scores obtained by our models improve by 3.9%and 14.5%,respectively.

关键词： temporal relation extraction neural network Attention mechanism graph attention network

维普期刊数据库

Efficient Unsupervised Image Stitching Using Attention mechanism with Deep Homography Estimation

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 1319-1334页

作者： Chunbin Qin Xiaotian Ran School of Artificial Intelligence Henan UniversityZhengzhou450000China

Traditional feature-based image stitching techniques often encounter obstacles when dealing with images lackingunique attributes or suffering from quality degradation. The scarcity of annotated datasets in real-life scenesseverely undermines the reliability of supervised learning methods in image stitching. Furthermore, existing deeplearning architectures designed for image stitching are often too bulky to be deployed on mobile and peripheralcomputing devices. To address these challenges, this study proposes a novel unsupervised image stitching methodbased on the YOLOv8 (You Only Look Once version 8) framework that introduces deep homography networksand attentionmechanisms. Themethodology is partitioned into three distinct stages. The initial stage combines theAttention mechanism with a pooling pyramid model to enhance the detection and recognition of compact objectsin images, the task of the deep homography networks module is to estimate the global homography of the inputimages consideringmultiple viewpoints. The second stage involves preliminary stitching of the masks generated inthe initial stage and further enhancement through weighted computation to eliminate common stitching artifacts.The final stage is characterized by adaptive reconstruction and careful refinement of the initial stitching results.Comprehensive experiments acrossmultiple datasets are executed tometiculously assess the proposed model. Ourmethod’s Peak Signal-to-Noise Ratio (PSNR) and Structure Similarity Index Measure (SSIM) improved by 10.6%and 6%. These experimental results confirm the efficacy and utility of the presented model in this paper.

关键词： Unsupervised image stitching deep homography estimation YOLOv8 Attention mechanism